<i>In Silico</i> Functional Profiling of Small Molecules and Its Applications

Sato, Tomohiro; Matsuo, Yo; Honma, Teruki; Yokoyama, Shigeyuki

doi:10.1021/jm800504q

Cited by 16 publications

(12 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the earlier applications in the field [100] employed SVMs to generate classification models for a total of 125 molecular functions which were derived from the MDDR database. Models were generated using MDL keys for a total set of 70 molecular actions and 55 therapeutic areas and 871 marketed drugs were analyzed with respect to their in silico bioactivity profile.…”

Section: Applications Of Machine Learning Based Target Prediction Metmentioning

confidence: 99%

From in silico target prediction to multi-target drug design: Current databases, methods and applications

Koutsoukas

Simms²,

Kirchmair

et al. 2011

Journal of Proteomics

248

182

View full text Add to dashboard Cite

Section: Applications Of Machine Learning Based Target Prediction Metmentioning

confidence: 99%

From in silico target prediction to multi-target drug design: Current databases, methods and applications

Koutsoukas

Simms²,

Kirchmair

et al. 2011

Journal of Proteomics

248

182

View full text Add to dashboard Cite

“…In every measurement, the larger value shows the better performance. Sato et al [23] described that accuracy (TP + TN)/(TP + FP + TN + FN) is not an appropriate measure when applying to unbalanced data. Obviously, the data set of the present study is unbalanced because the number of positive examples is much smaller than that of negative examples in every case.…”

Section: Evaluation Of the Classification Performancesmentioning

confidence: 99%

Identification of the Dual Action Antihypertensive Drugs Using TFS-Based Support Vector Machines

Kawai

Takahashi

2009

CBIJ

View full text Add to dashboard Cite

Recently, many concerns are paid for dual action drugs such as ACE/NEP dual inhibitors which have two different biological activities. To identify multiple active drugs by supervised learning approach, a multi-label classification technique is required. In the present work, we investigated the classification of antihypertensive drugs including ACE/NEP dual inhibitors using support vector machines (SVMs). Biological activity data of the drugs were taken from the MDDR database and they were employed for the computational trial for the training of the SVM classifiers. Structural feature representation of each drug molecule was based on topological fragment spectra (TFS) method. The obtained classifiers were tested for finding ACE/NEP dual inhibitors. The result suggests that the TFS-based SVM classifiers are useful for finding multiple active drugs such as ACE/NEP dual inhibitors.

show abstract

“…Interestingly, prediction of topoisomerase interaction of drugs in this same MDDR database of launched drugs by the Support Vector Machine (SVM) algorithm which is capable of drawing functional inference from a large number of structural features, also identified molecules with N ‐aryl ketones, N ‐dialkyls and fused ring planar compounds [Sato et al, , and personal communication]. Of 75 drugs predicted to be topo‐active, 22 were N ‐aryl ketones, seven were N ‐dialkyls, and eight were fused planar molecules.…”

Section: Discussionmentioning

confidence: 99%

Prediction of noncovalent Drug/DNA interaction using computational docking models: Studies with over 1350 launched drugs

Snyder

Holt

Maguire

et al. 2013

Environ and Mol Mutagen

View full text Add to dashboard Cite

Noncovalent chemical/DNA interactions, for example, intercalation and groove-binding, may be more important to genomic integrity than previously appreciated, and there may very well be genotoxic consequences of that binding. It is of importance, then, to develop methods allowing a determination or prediction of such interactions. This would have particular utility in the pharmaceutical industry where genotoxicity is, for the most part, disallowed in new drug entities. We have previously used DNA docking simulations to assess if molecules had structure and charge characteristics which could accommodate noncovalent binding via, for example, electrostatic/hydrogen bonding. We here extend those earlier studies by examining a series of over 1,350 "launched" drugs for ability to noncovalently bind 10 different DNA sequences using two computational programs: Autodock and Surflex. These drugs were also evaluated for binding to the crystallographic ATP-binding site of human topoisomerase II. The results obtained clearly demonstrate multiple series of noncovalent DNA binding structure activity relationships which would not have been predicted based on cursory structural examination. Many drugs within these series are genotoxic although not via any commonly recognized structural covalent alerts. The present studies confirm previously implicated features such as N-dialkyl groups and specific N-aryl ketones as potential genotoxic chemical moieties acting through noncovalent mechanisms. These initial studies provide considerable evidence that DNA intercalation may be an important, largely overlooked, source of drug-induced genotoxicity and further suggest involvement of topoisomerase in that genotoxicity.

show abstract

In Silico Functional Profiling of Small Molecules and Its Applications

Cited by 16 publications

References 67 publications

From in silico target prediction to multi-target drug design: Current databases, methods and applications

From in silico target prediction to multi-target drug design: Current databases, methods and applications

Identification of the Dual Action Antihypertensive Drugs Using TFS-Based Support Vector Machines

Prediction of noncovalent Drug/DNA interaction using computational docking models: Studies with over 1350 launched drugs

Contact Info

Product

Resources

About